Back to skill

Security audit

二手车验车清单台

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Chinese-language used-car inspection checklist skill with no code execution, persistence, credential access, or hidden data handling.

Before installing, note that this skill is geared toward Chinese-language used-car inspection workflows and may trigger on broad used-car phrases. Treat its output as a checklist and decision aid, not a replacement for a professional vehicle inspection, current local pricing research, or legal/transfer verification.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger list includes broad, common phrases such as “二手车” and “买车注意”, which can match many ordinary conversations and cause the skill to activate unexpectedly. Unintended invocation can expose users to irrelevant advice, override a more appropriate skill, or create prompt-routing confusion, especially in systems that auto-select skills based on loose keyword matching.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

The natural-language instructions and examples are entirely Chinese, and the skill does not state that users may choose another language or that the Chinese-only behavior is intentional for a specific regional use case. Under the policy, forcing a specific language without user opt-in can be a locale/language policy issue.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.